@inproceedings{hua-etal-2025-eot,
    title = "{E}o{T}: Evolution of Thoughts for Complex Reasoning Tasks",
    author = "Hua, Qin  and
      Sun, Jiaqi  and
      Qian, Shiyou  and
      Yang, Dingyu  and
      Cao, Jian  and
      Xue, Guangtao",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.1297/",
    doi = "10.18653/v1/2025.findings-emnlp.1297",
    pages = "23864--23886",
    ISBN = "979-8-89176-335-7",
    abstract = "Knowledge-based complex reasoning remains a significant challenge for large language models (LLMs) with in-context learning. To tackle this issue, previous studies focus on ensuring behavior fidelity, factuality, or reliability in generated reasoning processes that guide LLMs to produce solutions. However, these studies often neglect the simultaneous optimization on all these three aspects for each thought. The main challenges are the lack of comprehensive assessment mechanisms and the difficulty of efficient thought-level optimization. This paper introduces the Evolution of Thoughts (EoT) framework, which enhances the factuality, fidelity, and reliability of each thought in the reasoning process through a few LLM inferences. We propose a thought assessment method that is sensitive to knowledge and LLM behaviors, using three scorers to evaluate each thought by considering domain context, semantic alignment, and behavior impact. Additionally, we establish a self-reflective evolution mechanism to facilitate each reasoning process generation in a single-forward inference. Extensive experiments demonstrate that, for knowledge-based complex tasks, EoT improves the factuality and fidelity of reasoning processes by approximately 16.5{\%} and 48.8{\%}, respectively, while enhancing LLM reasoning capability by about 6.2{\%}, outperforming advanced approaches."
}